Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    deep dive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्ज
    1.02
    να
    0.99
    omag
    0.96
    शुदा
    0.96
    нг
    0.96
     égaux
    0.95
    νας
    0.95
     सर्वोच्च
    0.94
    ycin
    0.93
     soleil
    0.93
    POSITIVE LOGITS
     (>
    1.26
    邃
    1.19
    detalle
    1.14
    ்கு
    1.03
    С
    0.99
    f
    0.98
    p
    0.97
    IN
    0.95
     nhánh
    0.95
    кте
    0.93
    Act Density 0.007%

    No Known Activations